<![CDATA[This study applied statistical time series analysis to examine malaria cases among children aged 0–5 years in Primary Health Care (PHC) centers in Damaturu, Yobe State, using monthly data from 2017 to 2024. The study aimed to describe malaria patterns, examine long-term trends, identify seasonal components, fit an appropriate Seasonal Autoregressive Integrated Moving Average (SARIMA) model, and forecast future malaria incidence. Descriptive analysis showed a sharp increase in cases from 3,503 in 2017 to 25,412 in 2024, with a total of 109,101 cases recorded during the study period. Seasonal decomposition revealed consistent peaks during the rainy months of August to October, with October recording the highest transmission levels. Stationarity was confirmed using the Augmented Dickey–Fuller test (p = 0.01). Model identification based on ACF, PACF, AIC, and BIC criteria selected SARIMA(2,0,0)(0,1,1)[12] with drift as the best-fitting model. Forecasts for 2025–2026 indicated continued increases in malaria incidence, with projected peaks exceeding 3,700 and 3,900 cases, respectively. The findings confirm a significant upward trend and strong seasonal variation in malaria incidence among children under five in Damaturu. This study concludes that malaria remains a persistent and increasing public health challenge in the study area. The findings contribute to public health surveillance and epidemiological forecasting by demonstrating the value of SARIMA-based modelling for anticipating seasonal malaria burden. Practical implications include the need to strengthen seasonal interventions, improve surveillance, enhance resource allocation, and adopt predictive modelling for timely malaria control. Future research should incorporate climatic and socio-behavioral variables to improve forecast accuracy.]]>
Copyrights © 2026
